[CI] Shard extended pooling model tests (#52322)

Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
Signed-off-by: khluu <khluu000@gmail.com>
This commit is contained in:
Kevin H. Luu
2026-08-14 15:11:41 -07:00
committed by GitHub
parent d87ef456ab
commit 549cef0b0b
+6 -2
View File
@@ -124,24 +124,28 @@ steps:
commands:
- pytest -v -s models/language/generation_ppl_test
- label: Language Models Test (Extended Pooling)
- label: Language Models Test (Extended Pooling) %N
device: h200_35gb
key: language-models-test-extended-pooling
timeout_in_minutes: 120
parallelism: 4
optional: true
source_file_dependencies:
- vllm/
- "!vllm/distributed/kv_transfer/"
- tests/models/language/pooling
commands:
- pytest -v -s models/language/pooling -m 'not core_model'
- pytest -v -s models/language/pooling -m 'not core_model' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
mirror:
amd:
dind: false
device: mi300_1
timeout_in_minutes: 95
parallelism: 2
depends_on:
- image-build-amd
commands:
- pytest -v -s models/language/pooling -m 'not core_model' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
- label: Language Models Test (MTEB)
key: language-models-test-mteb